{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MYGD3NWEKSFVOOJ3YWMEISCQLI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9ae38fb2e0cb2959d59975bb53fdee75512685ee0c57ba91b68fe946e20a8d59","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T11:48:20Z","title_canon_sha256":"7262d7d8cad66331ec68cbe120b1474dfbc2a2007e0e037e0b6115e240bc0928"},"schema_version":"1.0","source":{"id":"2601.22868","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22868","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22868v3","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22868","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"MYGD3NWEKSFV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MYGD3NWEKSFVOOJ3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MYGD3NWE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:cf5abfba35c894a0422f8d75f2822a7fd06e0ce02515492ab23be86f49e237c6","target":"graph","created_at":"2026-05-18T02:44:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"any detector reasoning from a global representation that conflates subject and context is provably non-identifiable: two different subject-context configurations can map to the same embedding while requiring opposite labels, and no such detector can be correct on both."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed disentangled subject- and context-aware representations in CC-CLIP can be learned from single images without additional supervision or labels that would reintroduce the original identifiability problem."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Conditional compatibility learning reframes anomaly detection as checking subject-context fit rather than global deviation, with CC-CLIP delivering state-of-the-art performance on contextual anomalies and competitive results on structural ones."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Global representations that mix subject and context are provably non-identifiable for context-dependent anomalies."}],"snapshot_sha256":"20c4e5ec9e4a2477f5a748eeeb926bc3675335bebd4e8fd9f267cf4f7c89300c"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"32c867292e2f1dfa84e8c463a809dea7c24bf876937ae0627602f54b462bcf39"},"paper":{"abstract_excerpt":"Anomaly detection usually assumes that abnormality is an intrinsic property of an observation. A defect is a defect, and a rare object is rare, regardless of where it appears. Many real-world anomalies do not work this way. A runner on a track is normal, but the same runner on a highway is not. The subject is unchanged; only the context makes it anomalous. This setting, long recognized as contextual anomaly detection, remains largely underexplored in modern vision-language systems. The difficulty is not merely empirical; it is formal. When anomaly labels depend on the relation between a subjec","authors_text":"Didier Stricker, Jason Rambach, Shashank Mishra","cross_cats":["cs.LG"],"headline":"Global representations that mix subject and context are provably non-identifiable for context-dependent anomalies.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T11:48:20Z","title":"Conditional Compatibility Learning for Context-Dependent Anomaly Detection"},"references":{"count":14,"internal_anchors":0,"resolved_work":14,"sample":[{"cited_arxiv_id":"","doi":"10.1016/j.neucom.2020.11.018","is_internal_anchor":false,"ref_index":1,"title":"URL https://cdn.openai.com/papers/ gpt-4.pdf. Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. Learning transferable visua","work_id":"3a786313-75bc-4877-865f-ee9272d0910d","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Section A presents additional model details","work_id":"e08c441a-4860-41e1-ae04-abeff48733db","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Section B describes implementation and training de- tails","work_id":"d6e45f12-ca24-4aad-ad75-9dcd188fe4c5","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Section C reports extended ablation studies and addi- tional quantitative results","work_id":"3690945b-45d6-4502-a3ab-6c056969fc10","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Section D details the construction, annotation protocol, and evaluation splits of the CAAD-3K dataset","work_id":"392b48b8-d3c8-49a8-b63d-5f5fbc3592fb","year":null}],"snapshot_sha256":"6b8cc12edff40daf372f2e9b24b6dd928a73c4bb52fc16cb66eeab3cb4995334"},"source":{"id":"2601.22868","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T09:55:17.723289Z","id":"34a56e77-a5c8-472f-8df8-170935ff4f6d","model_set":{"reader":"grok-4.3"},"one_line_summary":"Conditional compatibility learning reframes anomaly detection as checking subject-context fit rather than global deviation, with CC-CLIP delivering state-of-the-art performance on contextual anomalies and competitive results on structural ones.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Global representations that mix subject and context are provably non-identifiable for context-dependent anomalies.","strongest_claim":"any detector reasoning from a global representation that conflates subject and context is provably non-identifiable: two different subject-context configurations can map to the same embedding while requiring opposite labels, and no such detector can be correct on both.","weakest_assumption":"That the proposed disentangled subject- and context-aware representations in CC-CLIP can be learned from single images without additional supervision or labels that would reintroduce the original identifiability problem."}},"verdict_id":"34a56e77-a5c8-472f-8df8-170935ff4f6d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0c3d37c0611354eb65fd745428f31173906cab883d5de172bddd4213707d6f6f","target":"record","created_at":"2026-05-18T02:44:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9ae38fb2e0cb2959d59975bb53fdee75512685ee0c57ba91b68fe946e20a8d59","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T11:48:20Z","title_canon_sha256":"7262d7d8cad66331ec68cbe120b1474dfbc2a2007e0e037e0b6115e240bc0928"},"schema_version":"1.0","source":{"id":"2601.22868","kind":"arxiv","version":3}},"canonical_sha256":"660c3db6c4548b57393bc5984448505a3260422ebd7833fbb5da35ab993ec508","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"660c3db6c4548b57393bc5984448505a3260422ebd7833fbb5da35ab993ec508","first_computed_at":"2026-05-18T02:44:31.737338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:31.737338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DEND2INAoGCokctLBt+ESzNnlhhBzQm9DoMB3sHdpQjcuGp8Q/k2oHUSolOfnsxrUNNgxSF7KhF1CzcOREAIDg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:31.737974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.22868","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c3d37c0611354eb65fd745428f31173906cab883d5de172bddd4213707d6f6f","sha256:cf5abfba35c894a0422f8d75f2822a7fd06e0ce02515492ab23be86f49e237c6"],"state_sha256":"7ca32bfe1c2ba6c2617ce9823eff8e040776c5d0d2c5c75c8ed8af4287714e02"}